INDEX
Explanations
mentions of locations or events within a community
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1042
+0.13
0.4%
872
+0.12
0.4%
752
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
752
+0.13
0.04
1510
+0.12
0.04
382
+0.11
0.05
Negative Logits
répon
-0.61
pecuni
-0.60
prenota
-0.59
migli
-0.57
sappi
-0.57
soggior
-0.56
DMETHOD
-0.56
🕗
-0.55
exé
-0.55
rispond
-0.55
POSITIVE LOGITS
the
1.16
the
0.89
unspeak
0.83
THE
0.70
tne
0.68
tbe
0.68
indescri
0.67
tlie
0.63
shenan
0.61
ASPECTS
0.59
Activations Density 0.485%